End of training

all_results.json

@@ -1,15 +1,15 @@
 {
     "epoch": 30.0,
-    "eval_accuracy": 0.06506024096385542,
-    "eval_loss": 5.995445728302002,
-    "eval_runtime": 1.2236,
+    "eval_accuracy": 0.7397590361445783,
+    "eval_loss": 1.1226757764816284,
+    "eval_runtime": 0.9717,
     "eval_samples": 6,
-    "eval_samples_per_second": 4.904,
-    "eval_steps_per_second": 1.635,
-    "perplexity": 401.59564664926756,
-    "train_loss": 6.3856693662446125,
-    "train_runtime": 2805.3129,
+    "eval_samples_per_second": 6.175,
+    "eval_steps_per_second": 2.058,
+    "perplexity": 3.073066049722984,
+    "train_loss": 1.552490357146866,
+    "train_runtime": 2803.476,
     "train_samples": 229,
-    "train_samples_per_second": 2.449,
-    "train_steps_per_second": 0.62
+    "train_samples_per_second": 2.451,
+    "train_steps_per_second": 0.621
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 30.0,
-    "eval_accuracy": 0.06506024096385542,
-    "eval_loss": 5.995445728302002,
-    "eval_runtime": 1.2236,
+    "eval_accuracy": 0.7397590361445783,
+    "eval_loss": 1.1226757764816284,
+    "eval_runtime": 0.9717,
     "eval_samples": 6,
-    "eval_samples_per_second": 4.904,
-    "eval_steps_per_second": 1.635,
-    "perplexity": 401.59564664926756
+    "eval_samples_per_second": 6.175,
+    "eval_steps_per_second": 2.058,
+    "perplexity": 3.073066049722984
 }

runs/Apr22_12-19-25_cae8a96265c3/events.out.tfevents.1682169629.cae8a96265c3.876.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a9ac01ada2c639fa11946ff9792d93d37722a97d84bf8be706ceaa464f5ea1e
+size 411

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 30.0,
-    "train_loss": 6.3856693662446125,
-    "train_runtime": 2805.3129,
+    "train_loss": 1.552490357146866,
+    "train_runtime": 2803.476,
     "train_samples": 229,
-    "train_samples_per_second": 2.449,
-    "train_steps_per_second": 0.62
+    "train_samples_per_second": 2.451,
+    "train_steps_per_second": 0.621
 }

trainer_state.json

@@ -9,30 +9,30 @@
   "log_history": [
     {
       "epoch": 8.62,
-      "learning_rate": 0.0003563218390804598,
-      "loss": 6.498,
+      "learning_rate": 3.563218390804598e-05,
+      "loss": 2.043,
       "step": 500
     },
     {
       "epoch": 17.24,
-      "learning_rate": 0.00021264367816091953,
-      "loss": 6.3597,
+      "learning_rate": 2.1264367816091954e-05,
+      "loss": 1.539,
       "step": 1000
     },
     {
       "epoch": 25.86,
-      "learning_rate": 6.896551724137931e-05,
-      "loss": 6.3417,
+      "learning_rate": 6.896551724137932e-06,
+      "loss": 1.2681,
       "step": 1500
     },
     {
       "epoch": 30.0,
       "step": 1740,
       "total_flos": 6403012579676160.0,
-      "train_loss": 6.3856693662446125,
-      "train_runtime": 2805.3129,
-      "train_samples_per_second": 2.449,
-      "train_steps_per_second": 0.62
+      "train_loss": 1.552490357146866,
+      "train_runtime": 2803.476,
+      "train_samples_per_second": 2.451,
+      "train_steps_per_second": 0.621
     }
   ],
   "max_steps": 1740,